Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data.

BACKGROUND: With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP). METHODS: For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done. FINDINGS: 66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77-0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77-7·95), with a Pearson correlation of 0·57 (95% CI 0·56-0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79-0·84) for ischaemic cardiomyopathy and 0·92 (0·91-0·94) for hypertrophic cardiomyopathy. INTERPRETATION: Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function. FUNDING: Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg.

How to maximize QRS narrowing.

BACKGROUND: Cardiac resynchronization therapy (CRT) resulting in maximal QRS narrowing may be associated with improved outcomes. METHODS: Various atrioventricular (AV) delay settings, including the new SyncAV™ algorithm (St. Jude Medical/Abbott, St. Paul, MN, USA), aimed at maximal QRS narrowing were tested in an 81-year old CRT recipient. RESULTS: Maximal QRS narrowing from 160 to 100 ms was achieved with a manually programmed value of SyncAV™ -30 ms. At 2 months, the patient proved to be a CRT super-responder. CONCLUSION: SyncAV™ algorithm is a new way for effective QRS narrowing with potentially improved outcomes.

Influence of gender on systemic IL-6 levels, complication rates and outcome after major trauma.

BACKGROUND: While female gender was associated with lower rates of systemic inflammatory response syndrome (SIRS), sepsis and single and/or multiple organ failure (MOF), contradictory data suggest no correlation between gender and complication rates and/or outcome in trauma patients (TP). Here, we analyzed the gender influence on systemic interleukin (IL)-6 levels and outcome in TP. PATIENTS/METHODS: 343 TP with injury severity scores (ISS) ≥16 were included upon admittance to the emergency department (ED) and grouped to male (n=257) vs. female (n=86). Injury severity, vital signs, physiological parameters, length of intensive care unit (ICU) and in-hospital stay, outcome parameters including SIRS, sepsis, respiratory complications, single- and/or MOF and in-hospital mortality were analyzed. Systemic IL-6 levels during the first 10 post-injury days were determined daily. RESULTS: Age (45.0±1.0 vs. 48.2±2.1) and ISS (27.1±0.8 vs. 24.7±1.2) were comparable between both groups. Abbreviated Injury Scale (AIS) ≥3 of chest and abdominal body regions were significantly higher in male TP (chest:51.02% vs. 36.05%, abdomen:19.84% vs. 10.47%, p<0.05). IL-6 was significantly increased in male TP on post-injury days 1 and 2 (d1:363.9±72.58 vs. 163.7±25.98; d2:194.3±31.38 vs. 114.3±17.81pg/ml, p<0.05). Multivariate analysis excluded an association of increased chest or abdominal injury occurrence with IL-6 levels. Female vs. male TP had significantly lower SIRS and sepsis occurrence (SIRS:40.70% vs. 53.31%, sepsis:6.98% vs. 19.46%, p<0.05). There were no gender-based differences regarding ICU or in-hospital stay, single and/or MOF and respiratory complications. CONCLUSIONS: Taken together, higher systemic IL-6 levels after trauma are associated with enhanced susceptibility for SIRS and sepsis in male patients.